检索结果-内蒙古大学图书馆

16th International Conference on Social robotics, ICSR + InnoBiz 2024

作者： Xu, Yue Zhang, Yinlong Liu, Shuai Liu, Yuanhao Liang, Wei He, Hongsheng Shenyang University of Technology Shenyang110020 China Guangzhou Institute of Industrial Intelligence Guangzhou511458 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Computer Science The University of Alabama TuscaloosaAL35487 United States

ISBN: (纸本)9789819611508

Accurately tracking the robotic arm and human joints is crucial to ensure safety during human-robot interaction. However, traditional pose tracking methods often exhibit insufficient performance and robustness in complex environments. The variations in the robotic arm’s environment and posture make it challenging for traditional methods to accurately capture the positions and posture of its joints. Specifically, when addressing challenges such as high similarity, occlusion, background complexity, and joint recognition failures, they often struggle to provide reliable and accurate results. To address these challenges, this paper proposes a human-robot pose tracking algorithm based on a new convolutional neural network model. To enhance detection accuracy, an improved color detection module is introduced to resolve joint misclassification. A geometric perception module is designed to accurately locate joints even under occlusion. Additionally, innovative iEMA and DBB modules are incorporated. The iEMA module employs edge detection technology to dynamically adjust thresholds for correct matching by improving the edge matching process. The DBB module refines the boundary box parameters for precise localization by introducing adaptive bounding box updates in real-time. This algorithm also integrates human pose recognition, enabling real-time pose recognition, thereby facilitating more intelligent and natural human-robot interaction. The algorithm has been rigorously evaluated on a custom-designed robotic arm platform. Experimental results validate the algorithm’s effectiveness and feasibility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

On-orbit assembly control based on model predictive control and load online identification

引用

Advances in Space Research 2025年

作者： Li, Yuntao Xu, Zichun Zhao, Zhiyuan Zhuang, Lei Yang, Xiaohang Ma, Boyu Zhao, Jingdong Liu, Hong State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin150001 China

Space manipulator are essential for on-orbit assembly (OOA) tasks. This paper proposes an advanced control framework to address key challenges in Cartesian trajectory tracking and compliant assembly. First, a rigid-body dynamic model of the manipulator is established using CAD model and joint friction identification. A Linear Extended state Observer (LESO) is designed to mitigate system errors by modeling both parametric uncertainties and external disturbances as an extended state. Additionally, the method for selecting parameters of the LESO, along with its convergence proof, is presented. Second, a model predictive control (MPC) algorithm is employed to optimize the Cartesian trajectory of the manipulator in real time. By linearizing the Cartesian space trajectory, the MPC problem is formulated as a QP problem. Solving this QP problem in real-time allows for the optimization of the Cartesian space trajectory, thereby improving the trajectory tracking accuracy in Cartesian space. Finally, online identification of load parameters, sensor zero drift, and temperature drift enables effective compliant assembly control. Extensive experiments validate the proposed methods: (1) The Cartesian trajectory tracking error is maintained below 0.1 mm. (2) After sensor compensation for identified load parameters, zero drift, and temperature drift, the maximum force residual is 0.42 N, and the maximum torque residual is 0.1 N m. © 2025 COSPAR

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Tracking control of a Cushion Robot with Safe Autonomous Motion Considering Human-Machine Interaction Environment

引用

Journal of Dynamic systems, Measurement and control 2025年第4期147卷 041003页

作者： Sun, Ping Shan, Rui Chang, Hongbin Wang, Shuoyu School of Artificial Intelligence Shenyang University of Technology Shenyang110870 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110169 China Department of Intelligent Mechanical Systems Engineering Kochi University of Technology Kochi7828502 Japan

This study proposes a data-driven safety controller with velocity constraints for a cushion robot. We constructed a mathematical description of the human-machine interaction environment by decomposing the generalized input force and coefficient matrix in the dynamic model. We established a new equivalent data model, which considered various human-machine interaction environments using a pseudo-Jacobian matrix. A stochastic configuration network (SCN) estimation method for variations in the human-machine interaction environment was proposed, with hidden layer nodes added at random. We designed a safe autonomous navigation path and proposed a data-driven control method that limited the actual velocity while stabilizing the tracking error system. In addition, the desired motion velocity of the robot was designed. This approach has the advantage of ensuring safety at a specified velocity. We also demonstrated and validated the effectiveness of the proposed data-driven algorithm using simulation-based comparative analysis and an experimental study. Copyright © 2024 by ASME.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Improving Collision-Free Success Rate For Object Goal Visual Navigation Via Two-Stage Training With Collision Prediction

arXiv

引用

arXiv 2025年

作者： Lian, Shiwei Zhang, Feitian Robotics and Control Laboratory Department of Advanced Manufacturing and Robotics College of Engineering State Key Laboratory of Turbulence and Complex Systems Peking University Beijing100871 China

The object goal visual navigation is the task of navigating to a specific target object using egocentric visual observations. Recent end-to-end navigation models based on deep reinforcement learning have achieved remarkable performance in finding and reaching target objects. However, the collision problem of these models during navigation remains unresolved, since the collision is typically neglected when evaluating the success. Although incorporating a negative reward for collision during training appears straightforward, it results in a more conservative policy, thereby limiting the agent’s ability to reach targets. In addition, many of these models utilize only RGB observations, further increasing the difficulty of collision avoidance without depth information. To address these limitations, a new concept—collision-free success is introduced to evaluate the ability of navigation models to find a collision-free path towards the target object. A two-stage training method with collision prediction is proposed to improve the collision-free success rate of the existing navigation models using RGB observations. In the first training stage, the collision prediction module supervises the agent’s collision states during exploration to learn to predict the possible collision. In the second stage, leveraging the trained collision prediction, the agent learns to navigate to the target without collision. The experimental results in the AI2-THOR environment demonstrate that the proposed method greatly improves the collision-free success rate of different navigation models and outperforms other comparable collision-avoidance methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Blockchain-Empowered Trustworthy End-Edge Collaborative Computing via Rotating Multi-Agent DRL

引用

IEEE Transactions on Wireless Communications 2025年

作者： Xu, Chi Zhang, Peifeng Yu, Haibin Li, Yonghui Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang China University of Chinese Academy of Sciences Beijing China University of Sydney School of Electrical and Information Engineering Sydney Australia

Blockchain-empowered end-edge collaborative computing is a promising technology for enhancing the timeliness and trustworthiness of Industrial Internet of Things (IIoT). However, integrating task offloading with blockchain consensus inevitably escalates resource consumption across communication, computation, and energy domains. Thus, the joint optimization of task offloading, resource allocation and blockchain consensus is very important for IIoT. This paper studies a general end-edge collaborative computing scenario with multiple end devices and multiple edge servers. We first propose a novel dynamic blockchain (DBC) scheme by developing a dynamic leader election mechanism and designing a dynamic consensus waiting time window. Then, by fully considering the constraints of multi-task size and deadline, communication bandwidth, computing frequency, battery capacity, Byzantine fault tolerant and trustworthiness, we formulate the trustworthy processing efficiency (TPE) maximization problem with respect to end-edge task division, communication and computation resource allocation, leader election and consensus waiting window. To address this problem, we transform it into a Markov decision process and design a compound reward by fully considering the penalty for computing timeout and consensus failure. After that, we propose a rotating multi-agent deep reinforcement learning (R-MADRL) algorithm tailored to the proposed DBC scheme, where an entropy-based dual-critic DRL algorithm is proposed for rotating multi-agent training and decentralized execution. Extensive experiments validate the effectiveness and superiority of the proposed DBC with R-MADRL, where three benchmark DRL algorithms and three blockchain consensus schemes are compared. The results demonstrate that R-MADRL achieves stable convergence with more than 60.32% TPE reward than other algorithms while the task timeout ratio of DBC is reduced by more than 66.49% compared with other schemes. © 2025 Institute of El

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Insulators Defect Detection for Power Grid Based on Improved Yolov7 Algorithm 13

Insulators Defect Detection for Power Grid Based on Improved...

引用

13th International Conference on Intelligent control and Information Processing, ICICIP 2025

作者： Zhang, Zhiwei Zhuang, Yan Liang, Zhida Kong, Shuai Zhu, Shengyi School of Control Science and Engineering Dalian University of Technology Dalian China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Special Equipment Safety Testing Technology of Zhejiang Province Zhejiang Academy of Special Equipment Science Hangzhou China

ISBN: (纸本)9798331516147

High-current out-of-phase closed bus is an essential link in the transmission of electric energy and is widely used in thermal power stations, hydropower stations and nuclear power plants. Although these busbars have the advantages of excellent dustproof effect and strong magnetic shielding, they are susceptible to insulator aging and damage in long-term operation, posing a potential safety risk to the power grid. Due to the enclosed space inside the bus and the complexity of external maintenance tasks, manual inspection has problems such as inefficiency and low safety. In order to solve these problems, this paper proposes an improved detection algorithm based on Yolov7 for insulator defect detection in hydropower station scenarios. Because of the particularity of Yolov7 network structure and application scenarios, this paper proposes a Channel Feature Enhancement module to enhance the channel representation ability of the network. In addition, an Edge Feature Enhancement module is introduced to improve the boundary detection of insulators by enhancing the contrast between the target and the background. Considering the limitations of existing studies in specific scenarios and the scarcity of dataset, this paper constructs and accurately annotates an insulator defect detection dataset applied to hydropower station scenarios. Experimental results show that the improved-Yolov7-tiny algorithm in this paper achieves a balance between accuracy and inference speed. © 2025 IEEE.

关键词： Magnetic shielding

来源：评论

学校读者我要写书评

暂无评论

Global-state-Free Obstacle Avoidance for Quadrotor control in Air-Ground Cooperation

引用

IEEE robotics and Automation Letters 2025年第7期10卷 6688-6695页

作者： Zhang, Baozhe Chen, Xinwei Chen, Qingcheng Xu, Chao Gao, Fei Cao, Yanjun Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber- Systems and Control Hangzhou310027 China Zhejiang University Huzhou Institute Huzhou313000 China Shanghai Institute of Special Equipment Inspection & Technical Research Shanghai200062 China

CoNi-MPC [1] provides an efficient framework for UAV control in air-ground cooperative tasks by relying exclusively on relative states, eliminating the need for global state estimation. However, its lack of environmental information poses significant challenges for obstacle avoidance. To address this issue, we propose a novel obstacle avoidance algorithm, Cooperative Non-inertial frame-based Obstacle Avoidance (CoNi-OA), designed explicitly for UAV-UGV cooperative scenarios without reliance on global state estimation or obstacle prediction. CoNi-OA uniquely utilizes a single frame of raw LiDAR data from the UAV to generate a modulation matrix, which directly adjusts the quadrotor's velocity to achieve obstacle avoidance. This modulation-based method enables real-time generation of collision-free trajectories within the UGV's non-inertial frame, significantly reducing computational demands (less than 5 ms per iteration) while maintaining safety in dynamic and unpredictable environments. The key contributions of this work include: (1) a modulation-based obstacle avoidance algorithm specifically tailored for UAV-UGV cooperation in non-inertial frames without global states;(2) rapid, real-time trajectory generation based solely on single-frame LiDAR data, removing the need for obstacle modeling or prediction;and (3) adaptability to both static and dynamic environments, thus extending applicability to featureless or unknown scenarios. © 2016 IEEE.

关键词： Quadrotors Collision avoidance Dynamics Autonomous aerial vehicles Trajectory Laser radar Air to ground communication Real-time systems Modulation Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Feedforward Optimization Mechanism for Improving Industrial Robots Trajectory Tracking Performance through Iterative Learning

An Adaptive Feedforward Optimization Mechanism for Improving...

引用

robotics, control and Automation (ICRCA), International Conference on

作者： Chengzhi Wang Sikai Zhao Tianjiao Zheng Hegao Cai Jie Zhao Yanhe Zhu State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China

ISBN: (数字)9798331544577

ISBN: (纸本)9798331544584

This paper presents an adaptive feedforward optimization method based on iterative learning control mechanism, improving trajectory tracking accuracy from trial to trail. Conventional feedforward control researches focus on the precise prediction and compensation of torques, either by means of dynamic modelling and parameter identification or by data-driven approaches. However, there exists unpredictable time-delay for torques to work. The proposed method takes the previously less-concerned velocity feedforward part of the servo control system into consideration, and a self-adaptive fine-tuning mechanism is designed and established. The error measurement and feedforward optimization processes are integrated into an iterative learning framework to obtain efficiency and precision. The effectiveness of proposed method is validated by physical experiments on an EFORT ER15 industrial robot, and an averagely 90.71% error reduction is witnessed.

关键词： Accuracy Torque Parameter estimation Trajectory tracking Service robots Predictive models Industrial robots Feedforward systems Servosystems Tuning

来源：评论

学校读者我要写书评

暂无评论

Semi-Autonomous Navigation Based on Local Semantic Map for Mobile Robot

引用

Journal of Shanghai Jiaotong university(Science) 2025年第1期30卷 27-33页

作者： ZHAO Yanfei XIAO Peng WANG Jingchuan GUO Rui Department of Automation Institute of Medical RoboticsShanghai Jiao Tong UniversityShanghai200240China State Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240China State Grid Intelligence Technology Co. Ltd.Jinan250013China

Mobile robots represented by smart wheelchairs can assist elderly people with mobility *** paper proposes a multi-mode semi-autonomous navigation system based on a local semantic map for mobile robots,which can assist users to implement accurate navigation(e.g.,docking)in the environment without prior *** order to overcome the problem of repeated oscillations during the docking of traditional local path planning algorithms,this paper adopts a mode-switching method and uses feedback control to perform docking when approaching semantic *** last,comparative experiments were carried out in the real *** show that our method is superior in terms of safety,comfort and docking accuracy.

关键词： semi-autonomous navigation mobile robot semantic map voice interaction

来源：评论

学校读者我要写书评

暂无评论

Representation of Human Arm Dynamic Intents with An Electrical-Impedance-Tomography (EIT)-Driven Musculoskeletal Model for Human-Robot Interaction

引用

IEEE Transactions on robotics 2025年 41卷 3278-3296页

作者： Zheng, Enhao Liu, Xiaodong Xu, Chenfeng Zhou, Zhihao Wang, Qining State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Institute for Artificial Intelligence Peking University Beijing100871 China Faculty of Engineering School of Advanced Manufacturing and Robotics Peking University The Institute for Artificial Intelligence Beijing100871 China

Representing human arm dynamic intent is essential for efective human-robot interaction. Accurately and robustly decoding these intentions through mathematical modeling of neuromuscular processes poses signifcant challenges. This study introduces an EIT-driven musculoskeletal model which integrates an EIT sensing system with methods for muscle identifcation, parameter estimation, and musculoskeletal system modeling. Unlike existing muscle-signal techniques, EIT captures muscle activities from the anatomical cross-sectional plane, providing both activation dynamics and morphological features. We validated our method through multi-DoF wrist kinematics estimation under varying contraction intensities, arm endpoint stifness estimation, and robotic variable admittance control. Our approach achieves accuracy comparable to state-of-the-art methods while requiring fewer training samples and a more compact sensing system. The model incorporates physiological constraints, minimizing decoding errors and ensuring interaction safety. This method enables reliable intent decoding with practical training demands. Future work will enhance the EIT system for complex tasks. © 2025 IEEE. All rights reserved.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：